1) Dataset:
2) Papers:
Paper List:
Reading List:
To-do List:
Unfilter:
Non Maximum Suppresion (NMS):
Used to filter those BBoxes that badly predict the same object.
Only retain the candidate BBoxes with higher response.
Greedy NMS [19]:
Added classification confidence score in R-CNN as a reference.
Soft NMS [1]:
Add IoU score to consider the problem of the occlusion of an object (cause the degradation of confidence score).
DIoU NMS [99]:
Add the center point distance to the BBox screening process.
3) References: